一作ACL 2026Poster· Natural Language Processing
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
Nianyi Lin · Jiajie Zhang · Lei Hou · Juanzi Li
摘要
A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) is the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation during training. While existing methods approximate the log-l...